The mobile communication system revolutionized the way people communicate, entertain, doing their businessrnand educate. This results in the need and demand for mobile and Internet users to increasing everyrnday. Ethio telecom is a discoverer market in Eastern Africa with 66.8 million mobile connections as ofrnAugust 2018. According to Growth and Transformation Plan 2 (GTP2) of the Federal Democratic Republicrnof Ethiopia (FDRE), the total mobile subscriber is expected to reach 103 million and the mobile broadbandrnshare will be estimated to 35 million subscribers by 2020. Based on the company marketing report, 85.9%rnof the revenue is generating from mobile services.rnGPRS Tunneling Protocol (GTP) is the pivotal protocol used in Long Term Evolution (LTE) to assign thernInternet Protocol (IP) addresses to mobile terminals and manages the data communication path in a mobilerndata network. IP spooï¬ng attack is one of the most signiï¬cant attacks in the IP based communicationrnsystem and it is used as a stepping stone for most of the attacks. Ethio telecom deployed LTE since 2014,rnin 2018 there were 300,000 subscribers. This technology is starting to attract the intention of users as wellrnas the company and it is expected to be the next mobile communication technology. Dong W. Kang et al.rnconducted a detection approach of IP spooï¬ng attacks in a 3G network and several studies are conductedrnin machine learning-based network anomalies detection methodologies. However, to the best of researchesrnknowledge, there is no speciï¬c research that is conducted on machine learning-based IP spooï¬ng attackrndetection on the LTE network.rnThis study analyzes a machine learning-based IP spooï¬ng attack detection system. Three supervised machinelearningrnclassiï¬ers namely: Logistic Regression (LR), K- Nearest Neighbor (KNN) and Gaussian NavernBayes (GNB) are evaluated.The evaluation is based on best-suited metrics such as; sensitivity, speciï¬city,rnprecision, False Positive Rate (FPR) and computational time rather than stick on generic metrics like accuracy.rnEven though GNB scores the heights sensitivity of 99.93%, considering the other metrics KNN isrnreasonably considered as the best classiï¬er with a sensitivity of 99.89%, a speciï¬city of 99.96%, precisionrnof 99.93%, FPR of 0.03% and accuracy of 99.94%. However, in most cases of a real situation, KNN is notrnpreferred for practical implementation, since KNN is computationally intensive. As a result, consideringrncomputational time metrics as key metric for practical implementation, LR is reasonably recommended asrnthe best classiï¬er with a sensitivity of 99.82%, speciï¬city of 87.56%, precision of 79.87%, FPR of 12.43%,rnaccuracy of 91.62%, training and testing time of 0.506sec and 0.005sec respectively.